Corpus ID: 14246464

Prosodic Hierarchy as an Organizing Framework for the Sources of Context in Phone-Based and Articulatory-Feature-Based Speech Recognition

@inproceedings{HasegawaJohnson2009ProsodicHA,
  title={Prosodic Hierarchy as an Organizing Framework for the Sources of Context in Phone-Based and Articulatory-Feature-Based Speech Recognition},
  author={M. Hasegawa-Johnson and J. Cole and Ken Chen and Lal Partha and A. Juneja and Taejin Yoon and S. Borys and Xiaodan Zhuang},
  year={2009}
}
Automatic speech recognition (ASR) is like solving a crossword puzzle. Context at every level is used to resolve ambiguity: the more context we can bring to bear, the higher will be the accuracy of the ASR. One of the ways in which ASR uses context is by defining context-dependent phonological units. This paper reviews and applies two types of phonological units that we find useful in ASR: “phones” (segmental units), and “articulatory features” (units roughly corresponding to bundles of… Expand
2 Citations
A Generative Student Model for Scoring Word Reading Skills
A novel Gaussianized vector representation for natural scene categorization

References

SHOWING 1-10 OF 129 REFERENCES
Speaking in shorthand - A syllable-centric perspective for understanding pronunciation variation
Detection of phonological features in continuous speech using neural networks
Feature-based pronunciation modeling for automatic speech recognition
Syllable-based large vocabulary continuous speech recognition
A Predictive Model of Prosody Through Grammatical Interface: A computational Approach
Articulatory Phonology: An Overview
...
1
2
3
4
5
...